Abstract: The system and method for evaluating the amount of marker identifying precipitate in a cellular specimen on a microscope slide is disclosed. The automated microscope system performs a low magnification and high magnification scan of a cellular specimen to identify and confirm candidate objects of interest which correspond to cells containing a marker identifying precipitate. A regularly shaped area centered about a centroid computed for a candidate object of interest is used to define the pixels to be processed. A color ratio is computed for each pixel and those color ratios indicative of being dominated by the color corresponding to the marker identified precipitate are summed and normalized. The normalized color ratio is compared to at least one predetermined threshold to assign a grade to the candidate objects of interest. The grades for a predetermined number of candidate objects of interest are summed to form an aggregate score and the aggregate score is compared to a threshold.

Abstract: An apparatus for transforming image data using a Wavelet transform, including an image compressing apparatus having a Wavelet transforming unit for compressing digitized image data and an image restoring apparatus having an inverse Wavelet transforming unit for restoring image data compressed by the image compressing apparatus. The Wavelet transforming unit in the image compressing apparatus includes a unit for extending image data area to make the number of data of the object of transform in horizontal and vertical directions, with every one octave of resolution lowered when a Wavelet transform is conducted hierarchically based on multiple resolution analysis, thereby conducting a Wavelet transform on data of the interpolated image data area. The inverse Wavelet transforming unit in the image restoring apparatus includes a unit for reducing redundant portion generated by extension of image data area in the image data compression, with every one octave of resolution increased.

Abstract: Document image data entered from a scanner are separated into a plurality of areas by an area separation unit. Attributes are assigned to respective ones of the plurality of partial areas obtained in the area separation unit. For instance, a character area in the main body of text and a character area in a table are examples of area attributes. Each of these attributes is assigned a degree of priority in advance. A character recognition/orientation discrimination unit detects character orientation in each of the plurality of partial areas and discriminates document orientation. The orientation of the document image data is determined based upon the document orientation of each partial area discriminated by the character recognition/orientation discrimination unit and the degree of priority of the attribute assigned to each partial area.

Abstract: Provided is a probabilistic statistical data compression/restoration method for variable-length encoding a source character and restoring a variable-length code to a character using the probability of occurrence of the source character which appears following a character string (context) of n characters which immediately precede the source character. When variable-length encoding is performed, a context registration unit successively registers context based upon an entered character without fixing the length (degree) of context, and a compressing encoder selects registered context satisfying a predetermined condition, e.g., registered context for which the frequency of occurrence is greater than a fixed value, as context (encoding context) used in encoding, and variable-length encodes a source character by using this encoding context. A restoration unit restores a code to a character by executing processing which is the reverse of the processing executed by the compressing encoder.

Abstract: Image to be transmitted is divided into blocks. The block size varies in each stage of transmission. The blocks are down-sampled to a fixed size for polynomial approximation coding (PAC). The PAC's are derived from a regressive model which is a statistical tool for data analysis. A two-dimensional polynomial equation is used to approximate the relation of the image data and their positions. The coefficients of the 2-D polynomial equation is coded and transmitted to represent the initial image. In the next stage, same or similar coding is conducted to the residual image. After a decided number of stages of transmission an approximated image is reconstructed. A novel iterative coding system for progressive image transmission is disclosed.

Abstract: The invention provides a character recognition apparatus wherein wrong correction in slant correction processing of a character string is minimized to minimize erroneous recognition. A character slant estimation section receives an image, calculates slant angle candidates and evaluation values of them, and calculates a slant angle estimated value based on the evaluation values. An estimated value evaluation section receives the evaluation values, calculates an information amount of the evaluation values or the like, and outputs it as a validity of the slant angle estimated value. A slant correction section receives and normalizes the validity to a value from 0 to 1 and determines the normalized value as an execution coefficient for slant correction.

Abstract: Image data representing a two-dimensional image is stored in N data storage devices driven in parallel. The two-dimensional image is divided into small divisional areas arranged in rectilinearly oriented lines and rows such that the number of areas in each line is equal to 2N and the number of areas in each row is equal to or less than 2N. The small divisional areas are stored in the N data storage devices such that no more than two of the areas in the same line are stored in the same storage device and no more of than two of the areas in the same row are stored in the same storage device. Additionally, two areas from the same line which are stored in the same storage device are positioned either adjacent to one another in the line or at opposite ends of the line and two areas from the same row which are stored in the same storage device are positioned either adjacent to one another in the row or at opposite ends of the row.

Abstract: A fast, memory efficient, and accurate document image matching system is disclosed. Document image matching is based on identifying anchor points of characters in the document. The document matching process includes a feature extraction step where anchor points, e.g., points representing approximate locations of characters, are identified as features for matching. In a particularly efficient implementation, the anchor points are "pass codes" in a two-dimensionally encoded representation of a document image.

Abstract: In an image forming apparatus which forms an image by parallel-processing an instruction set described in a page description language and in which image data can be efficiently processed by properly dividing the sequence of instructions for parallel-processing, interpreting means generates an intermediate representation independent of a language by interpreting an image plotting instruction described in a page description language according to a grammar of a page description language. The intermediate representation is divided into blocks according to a particle size designated by particle size designating means. Divided blocks are distributed by distributing means to converting means which can operate in parallel to each other and thereby converted into pixel representations. Partial converted pixel representations are synthesized by synthesizing means into a page image.

Abstract: Image data received from an original-document reading portion is stored in an image memory, and then transmitted to another facsimile apparatus. At this time, whenever image data for one communication is transmitted, information indicating a result of the transmission is stored. Also, image data received from a personal computer is stored in an image memory, and is then transmitted to the other facsimile apparatus. At this time, whenever image data for one communication is transmitted, information indicating a result of the transmission is stored. A communication management report is then output which enables identification to easily be performed with respect to whether image data supplied from the original-document reading portion has been transmitted or image data supplied from the personal computer has been transmitted.

Abstract: A method for processing compressed digital data derived from an original image sequence, the data being organized as a set of image frames, each image frame comprising a set of blocks, each block including a string of bits corresponding to an area of the original image frame in the original image sequence. A cost function is derived as a number related to the amount of bits spent to encode a block, sets of blocks, an image frame, or sets of image frames. A segmentation technique is applied to the map with cost functions. Temporal segmentation is performed by analyzing cost functions associated with each image frame. In both cases auxiliary functions can be used to improve the segmentation quality. The segmented regions of a image frame or sets of image frames can be identified, replaced, printed, or processed in special manners.

Abstract: An invention for determining a rectangular bounding box encompassing a photograph or object(s) represented within a digital image is disclosed. The rectangular bounding box is determined irrespective of the device used to acquire the digital image. First a set of contrast points is derived; these contrast points representing changes in the characteristics of a pixel from that of a traversed neighbor. After ordering the contrast points according to their radial angle around a central reference point, a list of lines is generated by selecting two points separated by q positions in the ordered list of contrast points. If the four lines generated the most often roughly form a rectangle, then they correspond to the sides of the rectangular bounding box. Else, the line with the highest count is used as a base side of the rectangular bounding box.

Abstract: An image is processed taking into account the direction of a predominant structure of the image. Said predominant direction is derived from image information in the image. In particular, the covariance matrix having matrix elements depending on products of differences between pixel-values in separate directions is calculated. The eigenvectors of the covariance matrix correspond with the predominant direction of the image structure and the eigenvalues of the covariance matrix represent the strength of the structure in the image. The covariance matrix is computed locally, i.e. for separate regions in the images so as to take variations of the direction of predominant structures into account.

Abstract: A method and apparatus, for arithmetically encoding input data, initialize a codeword table with K codewords, K being an integer greater than 1 and a probability value being assigned to each codeword. First to Mth symbols are extracted from the input data and M codewords are generated based thereon, with M being an integer representing a maximum length of codewords to be registered. First L symbols of the extracted M symbols are allocated with a probability of a longest registered codeword, wherein the longest registered codeword is the same as the first L symbols and L is an integer greater than 1. Then, the generated codewords except for the registered codewords are registered at the codeword table and probability values are reassigned to the registered codewords. After registering a predetermined number of codewords, the remaining symbols are sequentially allocated with the probability values of the corresponding registered codewords.

Abstract: In a three-dimensional shape extraction apparatus, a distance distribution extraction unit (54) obtains the distance distribution of an object on the basis of a plurality of images which are sensed by a camera at different image sensing positions, so that the images of the object partially overlap each other, and the position information of the respective image sensing positions of the camera. A three-dimensional model forming unit (55) forms a three-dimensional model of the object by sequentially combining the sequentially calculated distance distributions and the sensed images using the position information. A 3D display image generation unit (56) generates and displays a two-dimensional image from the three-dimensional model.

Abstract: A method for designating an object image to be extracted is simplified. Positions of contour designation points are designated by employing an operation input apparatus so that a contour region of an initial region containing a desirable subjective object image is designated. A central processing circuit firstly subdivides the basic image into a plurality of division regions which are like in color, in units of pixel groups. Subsequently, the central processing circuit calculates distances between pixels within the division region and pixels within the contour region, and also calculates positions of pixels with respect to the initial region, and then determines factor values for the respective pixels on the basis of distance values indicative of the distance and the position.

Abstract: An image generation apparatus of the present invention reduces the write access frequency to a plurality of memories and increases the image generation speed. The image generation apparatus divides an image zone into a plurality of blocks and assigns an address for each pixel within a block. In order to store the pixels within a shortened time, a parallel storing of the pixel shall be performed evenly at the grouping stage for storing them into respective FIFOs in accordance with the difference of the least significant bit of the address data of the pixel. In this case, the present invention bisects the binary address signal into high order address bits and low order address bits, takes an exclusive OR among the least significant bits of high and low order address bits and replace the least significant bit of the low order address bits with the result of the exclusive OR for the grouping discrimination sign.

Abstract: The spatial resolution of a multispectral digital image is enhanced in a process of the type wherein a higher spatial resolution panchromatic image is merged with a plurality of lower spatial resolution spectral band images. A lower spatial resolution panchromatic image is simulated and a Gram-Schmidt transformation is performed on the simulated lower spatial resolution panchromatic image and the plurality of lower spatial resolution spectral band images. The simulated lower spatial resolution panchromatic image is employed as the first band in the Gram-Schmidt transformation. The statistics of the higher spatial resolution panchromatic image are adjusted to match the statistics of the first transform band resulting from the Gram-Schmidt transformation and the higher spatial resolution panchromatic image (with adjusted statistics) is substituted for the first transform band resulting from the Gram-Schmidt transformation to produce a new set of transform bands.

Abstract: Spatial locations of individual points on an inaccessible object are determined by measuring two images acquired with one or more cameras which can be moved to a plurality of positions and orientations which are accurately determined relative to the instrument. Once points are located, distances are easily calculated. In distinction to prior art, which uses a fixed separation of camera viewpoints, this new system offers smaller errors, measurement over a larger range of object distances, and measurement of distances which cannot be contained in a single camera view. Random errors are minimized by use of an optimum measurement geometry. Systematic errors are minimized by use of a complete and robust set of calibration procedures. A standard measurement procedure automatically obtains the optimum measurement geometry. A least squares calculation uses all of the image location and calibration data to derive the true three dimensional positions of the selected object points.

Abstract: In forming a panoramic picture image by compositing picture images dividedly imaged, the invention corrects deviations of images of an object at overlap regions caused by a difference in fields of view of imaging means or movement of an object to be imaged in which a picture image forming apparatus includes a picture image inputting device, a frame memory for storing divided picture images inputted from the picture image inputting device, a picture image position calculating unit for calculating positions of compositing the divided picture images, a picture image parallax sampling and processing unit for sampling parallax information among picture images from picture images including parallaxes in the overlap regions among contiguous divided picture images, an intermediate picture image forming and processing unit for forming a plurality of intermediate picture images from the picture images including the parallaxes and a picture image composition and processing unit for compositing a panoramic picture image